A

ai-agents

AER-1 hub: guides, collectors, and the verifiable receipt standard.

Populates an empty Git repository with scaffolding files and folders for development of CLI tools, libraries, and (micro) services for C++, Go, and Java. The pre-populated repository is prepared for specification driven development with support of an AI coding assistant (Claude Code and GitHub Copilot, albeit to a lesser degree).

Production source of scriptmasterlabs.com — MCP servers and x402 paid-API gateway for the agent economy: provider trust verification, web research, URL-to-Markdown, stock quotes, currency conversion, fact checking, web scraping.

Asami : Agentic System Administration MCP Infrastructure. An all-in-one MCP toolset for Planka, SSH, and human-agentic cooperative workflows: code developement, system and network administration, specification production, and other tasks.

A self-hosted team of always-on AI agents for Linux — spread across as many machines as you own. Create named teammates, message them like colleagues, and hand off real work — they run in their own podman containers with sudo, remember everything, share files with each other, and only come back when they need your approval.

Wish to reality: AI agents engineer physical objects. R&D + products. Source-available, copyright reserved.

Long-running autonomy for Pi: draft goals, build projects from specs, run audited task queues, and recover interrupted work. Independent auditors verify completion.

Red-team drills that decide your AI agents' autonomy per DevSecOps stage. GitLab Transcend Life After Code entry (MIT).

RMI MCP server — 210+ crypto intelligence tools for AI agents, settled per call with x402 USDC payments.

Every AI-written code fix must survive an attack by a second AI, with proof, before it reaches production. A GitLab Duo DevSecOps loop: adversarial re-attack, a permanent antibody bank, and a deterministic anti-cheat Warden.

Zambo: the verifiable work layer for AI. AER-1 kit, verifier, and conformance suite.

Toolkit local-first de agentes IA para OpenCode. Orquesta subagentes cloud (OpenCode Go) y locales (Ollama), con memoria persistente (engram), OCR local (uocr) y generación/edición de imágenes (ComfyUI). Incluye dos agentes primary — agente-pobre (orquestador, optimización de costo) y agente-hacker-pobre (pentesting ético autorizado + auditoría de seguridad) — con skills de SAST/pentest, y un vault Obsidian de conocimiento. TypeScript (bun) + plugins de OpenCode.

Unofficial: one CLI over three always-on agents (ChatGPT Your dot, Grok Bot, Meta Muse). Wraps chatgpt-dot-cli, grok-bot-cli (gbot), and muse-web-cli. Not affiliated with OpenAI, xAI, Cursor, or Meta.

postgresai – Postgres observability built for humans and AI agents

Multi-platform AI dev-team orchestration with a single canonical knowledge base. Plan-Approve-Execute workflows, validation gates, projected to GitHub Copilot, Gemini CLI, Opencode, and Cursor.

Broadcast queries to 10 AI models in parallel, chat with individual models (supporting vision inputs), and watch them engage in live debates inside an AI Debate Chamber featuring real-time argument summaries and consensus verdicts. Built with FastAPI and a responsive HTML/JS UI.

Versioned project blueprints, agent instructions, service profiles, and platform workflows for AI-assisted project delivery.

Run Hermes Agent as a DataRobot workload with a web UI, Slack bot, persistent state, and CI/CD deploys. Community maintained.

Local-first AI agent memory and context engine for Claude Code, Codex, Gemini and MCP: cited Markdown recall, code search, hooks and cross-machine serving.

Production-grade memory operating system for agentic AI. Interoperates with every major framework via MCP, OpenAI-compatible gateway, and native /v1/* REST — Claude Code, OpenClaw, ZeroClaw, Hermes, MemPalace, LangChain, LlamaIndex, CrewAI, AutoGen, Mem0, Letta, Zep. In production use since December 2025. Apache 2.0.